Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
cyberrealisticXL_v22.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<cyberreal22-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
Cyberdelia
on Civitai
Creator notes
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff. 👉 💬 This is the model you reach for when you want super clean, photo-realistic results. It’s sharp, powerful, and somehow just nails gorgeous images every single time. ⚙️ Recommended Settings Sampling method: DPM++ 2M SDE Karras VAE: is already Baked In Sampling steps: 30+ Steps Resolution: 832x1216 / 896x1152 CFG: 3-5 Clip Skip: 1 Upscale: 1.5 upscale (0.3 - 0.35 denoise) Upscalers: 4x_NickelbackFS_72000_G / 4x_foolhardy_Remacri / 4x_NMKD-Siax_200k ⚙️ Recommended Settings DMD2 Sampler: LCM Schedule Type: Exponential Sampling Steps: 8/12 (12 for extra detail) CFG Scale: 1-1.5 ⚡ These settings are not the same as the standard SDXL workflow — be sure to adjust your pipeline! 💡 What’s the difference between FP16 and FP32 checkpoints? FP16 (half precision) uses 16-bit floating-point weights. It’s smaller in size, loads faster, and uses less VRAM - perfect for normal image generation. You won’t notice any visual difference for inference, so it’s ideal for everyday use. FP32 (full precision) uses 32-bit weights, which means it’s larger and heavier on resources. It doesn’t improve generation quality, but it’s better if you’re training, merging, or fine-tuning models, since it keeps the exact weight data without rounding loss. 🧠 Prompting Example negative prompt: cartoon, illustration, anime, painting, CGI, 3D render, low quality, watermark, logo, label or use ✨ Optional Adetailer Adetailer model: face_yolov9c.pt If you only want the main face being refined set 'Mask only the top k largest' to 1. 🔗 Links Backup location: ☕ Fuel the Project If this model gave you stellar results, . Or two. Or, you know… a GPU. ⚠️ Heads-Up This model can make mature or sensitive content. You’re fully responsible for what you create, so use it responsibly (or if you can’t resist, at least be artistically irresponsible). 💬 Want Better Prompts? Use this custom ChatGPT to auto-generate polished prompts for CyberRealistic XL: 🔗 []
9,052 downloads · 457 likes on Civitai
SHA256
779ED5CD37566050E4B4043D1C251F0E3F167365ADC5F099A658E4AD4038DD91
ModelTrends.ai Model ID
#3528
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DPM++ SDE
Steps
60
Guidance
2
Seed
3425609126
Size
896x1152
Prompt
Photorealistic, Low angle shot, soft lighting, film noise, giant Minotaur, Bull Head, holding a gold scepter, big black horns, fierce malevolent expression, extremely muscular, body covered in tick fur, big gold ring piercing in nose, wearing insane details golden armor, scaled armor, damned crown between horns, standing in throne hall, looking to camera, throne behind in background, Realistic details, Fantastic scene, Cinematic, dramatic cast shadows, high contrast, dark warriors in the background, <lora:detailed_notrigger:0.75>, <lora:MJ52_v1.3:0.75>
Negative prompt
Nude, NSFW, looking away, anime, cartoon, comic, 3D, CGI
Settings
Sampler
Euler a
Steps
35
Guidance
8
Seed
4129563414
Size
864x2048
Prompt
(masterpiece,Distinguished Quality,Mirror-like,Cinematic Experience,insanely detailed,absurdres),8k,wallpaper,,(Best illustrations:2.0),(One Woman:2.0),(Motoko Kusanagi:2.0),(Ghost in the Shell-style worldview:2.0),(Black tactical bodysuit:2.0),(Heavy black bulletproof vest:2.0),(Black gloves:2.0),(Short Bob:2.0),(Beautiful Eyes),(Detailed face),(Detailed female hand drawing:2.0),(sexy:2.0),(He kneels down and aims a pistol at me.:2.0),(Raise your right knee:2.0),(The background is Tokyo, where science and technology have developed.:2.0),(Drawing in monochrome:2.0),(sf:2.0),(A pistol with a laser pointer under the muzzle:2.0),(Point the red laser pointer on your pistol at me:2.0),
Negative prompt
(unrealistic), blurry, low quality, deformed, disfigured, anime, drawing, painting, illustration, comic, cartoon, simple background, blur, low quality, fairy, fairy wings, elf ears, censored , cross-eyed, (lazy eye), bucktooth, ugly, anime, deformed, dismembered, disembodied, detached, polydactyl, amputated, contorted, jpeg artifacts, signature, watermark, username, smile, happy
Settings
Sampler
DPM++ SDE
Steps
30
Guidance
5
Seed
3175431270
Size
768x1024
Prompt
Photo portrait of a 21 y.o. Dutch woman, defiant, pensive, freckles, long dark straight blonde hair, blue eyes
Negative prompt
(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4)
Settings
Sampler
dpmpp_2m_karras
Steps
30
Guidance
5
Seed
695562802825952
Size
832x1216
Prompt
a photo portrait of a beautiful girl with curls and lots of freckles, (ginger hair), (detailed eyes), (upper body portrait:1.5), dramatic light, Rembrandt lighting scheme, (hyperrealism:1.2), (8K UHD:1.2), (photorealistic:1.2), shot with Canon EOS 5D Mark IV, detailed face, detailed hair, embarrassed, exposed beats, perfect natural breasts, perfect nipplesfull body photo of a 23 year old Dutch woman, undercut hairstyle, tee, leather jacket, jeans, 80s convenience store, very detailed, atmospheric haze, film grain, cinematic film still, shallow depth of field, highly detailed, high budget, cinemascope, moody, epic, gorgeous, 2000s vintage RAW photo, photorealistic, color graded cinematic, eye catchlights, atmospheric lighting, skin pores, imperfections, natural, shallow dof
Negative prompt
(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4)
Settings
Sampler
DPM++ 2M Karras
Steps
40
Guidance
5.5
Seed
1376025815
Size
832x1216
Prompt
realistic photo of smoli, a cat, wearing a hat, looking at the viewer, (sharp focus, highly detailed, 4k, 8k, best quality, masterpiece, ultra highres:1), <lora:cat-smoli:1>
Negative prompt
extra limb, missing limb, floating limbs, (mutated hands and fingers:1.1), disconnected limbs, blurry, amputation, 3d, cgi, airbrushed, model, render, sketch, cartoon, drawing, anime
Settings
Sampler
DPM++ SDE
Steps
30
Guidance
5
Seed
3897866248
Size
768x1024
Prompt
a beautiful college girl, brunette, close-up, girl next door, baggy clothes, night, interior, messy hair, film grain, retro, (bokeh:1.3), Porta 160 color, shot on ARRI ALEXA 65, sharp focus on subject, Fujifilm XT-3
Negative prompt
(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4)
Settings
Sampler
DPM++ 2M Karras
Steps
40
Guidance
5.5
Seed
2616721262
Size
832x1216
Prompt
realistic photo of smoli, a cat, wearing a tuxedo, looking at the viewer, (sharp focus, highly detailed, 4k, 8k, best quality, masterpiece, ultra highres:1), <lora:cat-smoli:1>
Negative prompt
extra limb, missing limb, floating limbs, (mutated hands and fingers:1.1), disconnected limbs, blurry, amputation, 3d, cgi, airbrushed, model, render, sketch, cartoon, drawing, anime
Settings
Sampler
DPM++ 2M Karras
Steps
45
Guidance
5.5
Seed
1958255613
Size
832x1216
Prompt
realistic photo, (sharp focus, highly detailed, 4k, 8k, best quality, masterpiece, ultra highres:1)m <lora:fpz:0.88>, fpz, 1cat, cat, wearing a turtleneck sweater, wearing yoga pants
Negative prompt
extra limb, missing limb, floating limbs, (mutated hands and fingers:1.1), disconnected limbs, blurry, amputation, 3d, cgi, airbrushed, model, render, sketch, cartoon, drawing, anime
AI Models for Image, Video & Text Generation
cyberreal22 xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models